Human-Computer Co-Creativity in Music Improvisation

Recommended Prerequisites

Basic musical knowledge and motivation for group activity.

Teaching Methods

The methodology anchors the presentation of generative computational models, human-computer interaction, and project examples. This content is accompanied by two practical activities: 1) a programming laboratory where students will be able to develop programming linked to the models presented in the classroom; 2) students will use the programming environments SoMax2 and MAX-Msp to engage in practical activities related to improvisation.

Learning Outcomes

This curricular unit addresses the interaction between computational co-creativity and musical improvisation with acoustic instruments or digital interfaces. We introduced to students generative and evolutionary computational models, which allow the creation of computational improvisation systems capable of listening and adapting in real-time to human performance.

Work Placement(s)

No

Syllabus

1. Fundamentals of computational co-creativity and its application in music.

2. Generative and evolutionary computational models applied to music.

3. Human-computer interaction in improvised musical performances.

4. State of the art in computational improvisation systems.

5. Introduction to the SoMAX2 environment.

6. Design of improvisation systems.

Head Lecturer(s)

Pedro José Mendes Martins

Assessment Methods

Assessment
Apresentação e Discussão da Proposta do Grupo 20, Apresentação dos Dispositivos e Programação Desenvolvida 30, Performance Coletiva Final 50: 100.0%

Bibliography

Assayag, G., Dubnov, S., & Delerue, O. (1999). Guessing the Composer’s Mind: Applying Universal Prediction to Musical Style. 

Barbaresi, M., & Roli, A. (2022). Evolutionary Music: Statistical Learning and Novelty for Automatic Improvisation. In J. J. Schneider, M. S. Weyland, D. Flumini, & R. M. Füchslin (Eds.), Artificial Life and Evolutionary Computation (Vol. 1722, pp. 172–183). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-23929-8_17 

Dubnov, S., Assayag, G., Lartillot, O., & Bejerano, G. (2003). Using machine-learning methods for musical style modeling. Computer, 36(10), 73–80.

Moroni, A., Manzolli, J., Zuben, F. V., & Gudwin, R. (2000). Vox Populi: An Interactive Evolutionary System for Algorithmic Music Composition. Leonardo Music Journal, 10, 49–54. https://doi.org/10.1162/096112100570602

Scirea, M., Eklund, P., Togelius, J., & Risi, S. (2017). Primal-improv: Towards co-evolutionary musical improvisation. 2017 9th Computer Science and Electronic Engineering (CEEC), 172–177. https://doi.org/10.1109/CEEC.2017.8101620

Zacharakis, A., Kaliakatsos-Papakostas, M., Kalaitzidou, S., & Cambouropoulos, E. (2021). Evaluating Human-Computer Co-creative Processes in Music: A Case Study on the CHAMELEON Melodic Harmonizer. Frontiers in Psychology, 12, 603752. https://doi.org/10.3389/fpsyg.2021.603752.

http://repmus.ircam.fr/somax2

Wang, G., Trueman, D., Smallwood, S., & Cook, P. R. (2008). Erratum: The Laptop Orchestra as Classroom. Computer Music Journal, 32(2), 4–4. https://doi.org/10.1162/comj.2008.32.2.4a